# MINT: A Universal Zero-Shot Predictor for Transaction Data

arXiv: https://arxiv.org/abs/2608.14198 · HTML: https://mlsanity.com/paper/2608.14198/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Builds on (most cited first, 11 of 11)

- [Layer by Layer: Uncovering Hidden Representations in Language Models](https://mlsanity.com/paper/2502.02013/) (2025)
- [ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning](https://mlsanity.com/paper/2412.03104/) (2024)
- [Tabular Transformers for Modeling Multivariate Time Series](https://mlsanity.com/paper/2011.01843/) (2020)
- [SensorLM: Learning the Language of Wearable Sensors](https://mlsanity.com/paper/2506.09108/) (2025)
- [CoLES: Contrastive Learning for Event Sequences with Self-Supervision](https://mlsanity.com/paper/2002.08232/) (2020)
- [Towards a Foundation Purchasing Model: Pretrained Generative Autoregression on Transaction Sequences](https://mlsanity.com/paper/2401.01641/) (2024)
- [Scalable Representation Learning for Multimodal Tabular Transactions](https://mlsanity.com/paper/2410.07851/) (2024)
- [Your Spending Needs Attention: Modeling Financial Habits with Transformers](https://mlsanity.com/paper/2507.23267/) (2025)
- [PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling](https://mlsanity.com/paper/2510.10102/) (2025)
- [TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understanding](https://mlsanity.com/paper/2511.19693/) (2025)
- [Fine-grained Attention in Hierarchical Transformers for Tabular Time-series](https://mlsanity.com/paper/2406.15327/) (2024)

## Abstract (arXiv)

Banks analyse sequential financial transaction data to perform many tasks, including fraud prevention, credit risk assessment and offer personalization. To improve the predictive accuracy of these tasks, Payments Foundation Models encode transaction sequence data as rich contextual embeddings, which can then be provided to task-specific models as features. However, these Foundation Models are not designed for flexible zero-shot reasoning across novel downstream prediction tasks, limiting their adaptability and utility. Existing LLM-based approaches to zero-shot prediction often fail to fully exploit the predictive signal within transaction data, while relying on costly text serialization or task-specific architectures that scale poorly. To address these limitations, we present the Multimodal Instruction Network for Transactions (MINT), a framework that connects a pretrained transaction sequence encoder to a decoder-only LLM through lightweight embedding injection, transaction-language alignment, and instruction tuning. We find that MINT achieves state-of-the-art predictive question-answering performance in both in-distribution and out-of-distribution questions, while substantially reducing input tokens, latency, and memory consumption compared to text-serialization baselines. Through comprehensive analyses of representations, alignment strategies, training data, and history length, we establish that compact transaction embeddings are a superior approach to transaction representation than text serialization for multimodal reasoning and zero-shot prediction tasks.